Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3061 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.3291. Min Range: -5.3291

Max Act: 5.3269. Min Act: -0.0000

Data Index: 53212 (The Pile)

Max Activating Token Index: 656

Text #1

Max Range: 5.3291. Min Range: -5.3291

Max Act: 5.1682. Min Act: -0.0000

Data Index: 110590 (The Pile)

Max Activating Token Index: 411

Text #2

Max Range: 5.3291. Min Range: -5.3291

Max Act: 5.3291. Min Act: -0.0000

Data Index: 1872266 (The Pile)

Max Activating Token Index: 457

Text #3

Max Range: 5.3291. Min Range: -5.3291

Max Act: 5.1545. Min Act: -0.0000

Data Index: 119565 (The Pile)

Max Activating Token Index: 439

Text #4

Max Range: 5.3291. Min Range: -5.3291

Max Act: 5.1412. Min Act: -0.0000

Data Index: 167055 (The Pile)

Max Activating Token Index: 871

Text #5

Max Range: 5.3291. Min Range: -5.3291

Max Act: 4.8645. Min Act: -0.0000

Data Index: 1035160 (The Pile)

Max Activating Token Index: 484

Text #6

Max Range: 5.3291. Min Range: -5.3291

Max Act: 4.8067. Min Act: -0.0000

Data Index: 1584123 (The Pile)

Max Activating Token Index: 878

Text #7

Max Range: 5.3291. Min Range: -5.3291

Max Act: 4.8919. Min Act: -0.0000

Data Index: 246130 (The Pile)

Max Activating Token Index: 577

Text #8

Max Range: 5.3291. Min Range: -5.3291

Max Act: 4.2169. Min Act: -0.0000

Data Index: 285979 (The Pile)

Max Activating Token Index: 747

Text #9

Max Range: 5.3291. Min Range: -5.3291

Max Act: 4.5217. Min Act: -0.0000

Data Index: 158428 (The Pile)

Max Activating Token Index: 446

Text #10

Max Range: 5.3291. Min Range: -5.3291

Max Act: 4.4244. Min Act: -0.0000

Data Index: 1700481 (The Pile)

Max Activating Token Index: 882

Text #11

Max Range: 5.3291. Min Range: -5.3291

Max Act: 4.3560. Min Act: -0.0000

Data Index: 1741763 (The Pile)

Max Activating Token Index: 305

Text #12

Max Range: 5.3291. Min Range: -5.3291

Max Act: 4.0285. Min Act: -0.0000

Data Index: 811211 (The Pile)

Max Activating Token Index: 817

Text #13

Max Range: 5.3291. Min Range: -5.3291

Max Act: 3.9889. Min Act: -0.0000

Data Index: 710113 (The Pile)

Max Activating Token Index: 453

Text #14

Max Range: 5.3291. Min Range: -5.3291

Max Act: 3.9406. Min Act: -0.0000

Data Index: 1532833 (The Pile)

Max Activating Token Index: 564

Text #15

Max Range: 5.3291. Min Range: -5.3291

Max Act: 4.3458. Min Act: -0.0000

Data Index: 1855988 (The Pile)

Max Activating Token Index: 601

Text #16

Max Range: 5.3291. Min Range: -5.3291

Max Act: 4.0836. Min Act: -0.0000

Data Index: 889364 (The Pile)

Max Activating Token Index: 899

Text #17

Max Range: 5.3291. Min Range: -5.3291

Max Act: 3.9000. Min Act: -0.0000

Data Index: 98724 (The Pile)

Max Activating Token Index: 257

Text #18

Max Range: 5.3291. Min Range: -5.3291

Max Act: 4.0178. Min Act: -0.0000

Data Index: 1567007 (The Pile)

Max Activating Token Index: 763

Text #19

Max Range: 5.3291. Min Range: -5.3291

Max Act: 3.7849. Min Act: -0.0000

Data Index: 1455163 (The Pile)

Max Activating Token Index: 172